AI models can be ranked by their ability to generate questions that cause disagreement among other models, creating a self-scaling evaluation system.
hub
Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents
13 Pith papers cite this work, alongside 9 external citations. Polarity classification is still indexing.
13
Pith papers citing it
9
external citations · OpenAlex
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 13representative citing papers
ToolPrivacyBench is a new benchmark that evaluates purpose-bound privacy over-disclosure in multi-tool LLM agent trajectories by auditing tool arguments against policy knowledge bases across 2,150 cases.
AIRGuard is a runtime authority-control layer for tool-using agents that reduces attack success on AgentTrap from 36.3% to 5.5% while retaining higher benign utility than ARGUS or MELON on DTAP-150.
Empirical study finds LLM robustness to sensory prompt injections in robotic systems is model-specific rather than scale-dependent, with a hybrid firewall blocking known patterns but bypassed by obfuscated variants at 10.2% rate.
ActPlane introduces an OS-kernel policy engine using an information-flow control DSL and eBPF to enforce agent harness policies, achieving better compliance on indirect paths with 1.9-8.4% overhead.
Cordon is a transactional runtime system that binds tool intents to reversible state, staged effects, and audit metadata to validate composed agent workflows before commit.
SecureForge audits LLM code for vulnerabilities, builds a synthetic prompt corpus via Markovian sampling, and optimizes system prompts to cut security issues by up to 48% while preserving unit test performance, with zero-shot transfer to real prompts.
Pact is a choreographic language extended with game-theoretic operations that maps every protocol to a formal game for reasoning about agent decisions and solving for decision policies.
AI agents can generate code in a capability-safe Scala dialect that statically prevents information leakage and malicious side effects while preserving task performance.
Introduces Context-Fractured Decomposition (CFD) attacks exploiting provenance gaps in tool-using LLM agents to raise jailbreak success rates by up to 28.3 percentage points over baselines.
Analysis of 67,453 OpenClaw skills shows three scanners overlap on at most 10.4% of combined positives, with 81.9% flagged by only one scanner and distinct profiles for malicious versus suspicious skills.
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
Measuring Intelligence Beyond Human Scale
AI models can be ranked by their ability to generate questions that cause disagreement among other models, creating a self-scaling evaluation system.
-
ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
ToolPrivacyBench is a new benchmark that evaluates purpose-bound privacy over-disclosure in multi-tool LLM agent trajectories by auditing tool arguments against policy knowledge bases across 2,150 cases.
-
AIRGuard: Guarding Agent Actions with Runtime Authority Control
AIRGuard is a runtime authority-control layer for tool-using agents that reduces attack success on AgentTrap from 36.3% to 5.5% while retaining higher benign utility than ARGUS or MELON on DTAP-150.
-
RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots
Empirical study finds LLM robustness to sensory prompt injections in robotic systems is model-specific rather than scale-dependent, with a hybrid firewall blocking known patterns but bypassed by obfuscated variants at 10.2% rate.
-
ActPlane: Programmable OS-Level Policy Enforcement for Agent Harnesses
ActPlane introduces an OS-kernel policy engine using an information-flow control DSL and eBPF to enforce agent harness policies, achieving better compliance on indirect paths with 1.9-8.4% overhead.
-
Cordon: Semantic Transactions for Tool-Using LLM Agents
Cordon is a transactional runtime system that binds tool intents to reversible state, staged effects, and audit metadata to validate composed agent workflows before commit.
-
SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization
SecureForge audits LLM code for vulnerabilities, builds a synthetic prompt corpus via Markovian sampling, and optimizes system prompts to cut security issues by up to 48% while preserving unit test performance, with zero-shot transfer to real prompts.
-
Pact: A Choreographic Language for Agentic Ecosystems
Pact is a choreographic language extended with game-theoretic operations that maps every protocol to a formal game for reasoning about agent decisions and solving for decision policies.
-
Tracking Capabilities for Safer Agents
AI agents can generate code in a capability-safe Scala dialect that statically prevents information leakage and malicious side effects while preserving task performance.
-
Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps
Introduces Context-Fractured Decomposition (CFD) attacks exploiting provenance gaps in tool-using LLM agents to raise jailbreak success rates by up to 28.3 percentage points over baselines.
-
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
Analysis of 67,453 OpenClaw skills shows three scanners overlap on at most 10.4% of combined positives, with 81.9% flagged by only one scanner and distinct profiles for malicious versus suspicious skills.
-
Ghost in the Context: Policy-Carriage Integrity in LLM Agents
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.